© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12133
    Prev
    Next
    INDEX
    Explanations

    verbs relating to logical statements and sequences of actions

    oai_token-act-pair · gemini-2.0-flash

    subsequent actions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.46
     وتسجيلات
    -0.46
    findpost
    -0.46
     atof
    -0.43
    RunWith
    -0.43
     sécher
    -0.43
     pantaloni
    -0.41
     specchio
    -0.41
    ɚ
    -0.41
    τουργ
    -0.40
    POSITIVE LOGITS
    GEBURTSDATUM
    0.64
    AlterField
    0.61
     the
    0.57
    Produzione
    0.56
    obao
    0.55
    oredCriteria
    0.55
    shadowRadius
    0.54
    Šaltiniai
    0.54
    iastes
    0.54
    hringer
    0.54
    Activations Density 14.159%

    No Known Activations